Building NAS: Automatic designation of efficient neural architectures for building extraction in high-resolution aerial images
作者：
Highlights：
• The attempt of applying neural architecture search algorithm in segmentation of aerial images.
• More lightweight hierarchical search space for neural architecture search of segmentation task.
• Entropy regularized objective makes the searching process more effectively.
• Better trades off the accuracy and efficiency of neural networks by using neural architecture search.
• Achieved mIoU of 86.85% with only 2.05G Flops and 3.10 M parameters on WHUBuilding Dataset.
摘要
•The attempt of applying neural architecture search algorithm in segmentation of aerial images.•More lightweight hierarchical search space for neural architecture search of segmentation task.•Entropy regularized objective makes the searching process more effectively.•Better trades off the accuracy and efficiency of neural networks by using neural architecture search.•Achieved mIoU of 86.85% with only 2.05G Flops and 3.10 M parameters on WHUBuilding Dataset.
论文关键词：Convolutional neural network,Deep learning,Aerial images,Semantic segmentation,Neural architecture search
论文评审过程：Received 15 May 2020, Revised 23 June 2020, Accepted 15 September 2020, Available online 19 September 2020, Version of Record 2 October 2020.
论文官网地址：https://doi.org/10.1016/j.imavis.2020.104025
